<?xml version="1.0" encoding="UTF-8"?><oembed><type>video</type><version>1.0</version><html>&lt;iframe src=&quot;https://www.loom.com/embed/c4059e95012547cb9691ee8db3d307c1&quot; frameborder=&quot;0&quot; width=&quot;1920&quot; height=&quot;1440&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1440</height><width>1920</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1440</thumbnail_height><thumbnail_width>1920</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/c4059e95012547cb9691ee8db3d307c1-0997389caad1e42b.gif</thumbnail_url><duration>421.293</duration><title>Music Recommender RAG System Evaluation</title><description>I recorded a Loom explaining my Music Recommender RAG system. I ran a Python script from the src folder and it returned the top 10 songs with match scores based on genre, mood, and energy, then highlighted the top three recommendations for multiple natural language queries. I also ran an evaluator script to check how many tests passed against expected confidence scores, and all the status checks showed pass. This confirmed the scores aligned with the dataset in my CSV. I did not request any action from viewers.</description></oembed>